Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2872. Min Range: -6.2872
Max Act: 6.2872. Min Act: -0.1700
Data Index: 2678615 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2872. Min Range: -6.2872
Max Act: 6.2872. Min Act: -0.1700
Data Index: 3931314 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.9434. Min Act: -0.1700
Data Index: 329029 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.8497. Min Act: -0.1700
Data Index: 8205486 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.8497. Min Act: -0.1700
Data Index: 8248115 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.8497. Min Act: -0.1700
Data Index: 6517607 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.8184. Min Act: -0.1700
Data Index: 6061744 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.7872. Min Act: -0.1700
Data Index: 6824797 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.7872. Min Act: -0.1700
Data Index: 6578295 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.7559. Min Act: -0.1700
Data Index: 5712456 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.7559. Min Act: -0.1700
Data Index: 193983 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.7559. Min Act: -0.1700
Data Index: 3850604 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.7247. Min Act: -0.1700
Data Index: 6680857 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.7247. Min Act: -0.1700
Data Index: 3007023 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.6622. Min Act: -0.1700
Data Index: 697306 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.6622. Min Act: -0.1700
Data Index: 6181728 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.6309. Min Act: -0.1700
Data Index: 4169296 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.6309. Min Act: -0.1700
Data Index: 797156 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.6309. Min Act: -0.1700
Data Index: 8447479 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2872. Min Range: -6.2872
Max Act: 5.5997. Min Act: -0.1700
Data Index: 8774785 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19